Study of stress detection and proposal of stress-related features using commercial-off-the-shelf wrist wearables

  • Francisco de Arriba-PérezEmail author
  • Juan M. Santos-Gago
  • Manuel Caeiro-Rodríguez
  • Mateo Ramos-Merino
Original Research


This paper discusses the possibility of detecting personal stress making use of popular wearable devices available in the market. Different instruments found in the literature to measure stress-related features are reviewed, distinguishing between subjective tests and mechanisms supported by the analysis of physiological signals from clinical devices. Taking them as a reference, a solution to estimate stress based on the use of commercial-off-the-shelf wrist wearables and machine learning techniques is described. A mobile app was developed to induce stress in a uniform and systematic way. The app implements well-known stress inducers, such as the Paced Auditory Serial Addition Test, the Stroop Color-Word Interference Test, and a hyperventilation activity. Wearables are used to collect physiological data used to train classifiers that provide estimations on personal stress levels. The solution has been validated in an experiment involving 19 subjects, offering an average accuracy and F-measures close to 0.99 in an individual model and an accuracy and F-measure close to 0.85 in a global 2-level classifier model. Stress can be a worrying problem in different scenarios, such as in educational settings. Thus, the last part of the paper describes the proposal of a set of stress related indicators aimed to support the management of stress over time in such settings.


COTS wrist wearables Stress quantification Wearables analytics Wearable stress detection 



This work is supported by the Spanish State Research Agency, the European Regional Development Fund (ERDF) under the PALLAS (TIN2016-80515-R AEI/EFRD, EU) project and the employment contract granted by the University of Vigo in July 2016 for the performance of PhD studies.

Compliance with ethical standards

Conflict of interest

The authors declare no conflict of interest.


  1. Beck A, Steer R (1990) Manual for the Beck anxiety inventory. San Antonio, TX Psychol CorpGoogle Scholar
  2. Ben-Zeev D, Scherer EA, Wang R et al (2015) Next-generation psychiatric assessment: using smartphone sensors to monitor behavior and mental health. Psychiatr Rehabil J 38:218–226. CrossRefGoogle Scholar
  3. Brown TA, Chorpita BF, Korotitsch W, Barlow DH (1997) Psychometric properties of the Depression Anxiety Stress Scales (DASS) in clinical samplesGoogle Scholar
  4. Burns A, Greene BR, McGrath MJ et al (2010) SHIMMER™—a wireless sensor platform for noninvasive biomedical research. IEEE Sens J 10:1527–1534. CrossRefGoogle Scholar
  5. Caddy B (2018) Stress tracking tech: Heart rate monitoring and guided breathing devices. Accessed 15 Nov 2018
  6. Cano A, Miguel-Tobal JJ, González H, Iruarrizaga I (2007) Hiperventilación y experiencia de ansiedad. Ansiedad y Estrés 13:291–302Google Scholar
  7. Cano-Vindel A, Miguel-Tobal JJ (1999) Evaluación de la ansiedad desde un enfoque interactivo y multidimensional: el Inventario de Situaciones y Respuestas de Ansiedad (ISRA). Psicol Contemp 6:14–21Google Scholar
  8. Carroll B, Davidson J (2000) Screening Scale for DSM-IV GADGoogle Scholar
  9. Chandola T, Brunner E, Marmot M (2006) Chronic stress at work and the metabolic syndrome: prospective study. BMJ 332:521–525. CrossRefGoogle Scholar
  10. Cohen S, Williamson G (1988) Perceived stress in a probability sample of the United States. In: Spacapan S, Oskamp S (eds) The Soc Psychol Heal Claremont Symp Appl Soc Psychol Newbury Park CA SageGoogle Scholar
  11. Cohen S, Kamarck T, Mermelstein R (1983) A global measure of perceived stress. J Health Soc Behav 385–396Google Scholar
  12. Cola G, Vecchio A (2018) Wearable systems for e-health and wellbeing. Pers Ubiquitous Comput 22:225–225. CrossRefGoogle Scholar
  13. Colligan TW, Higgins EM (2006) Workplace Stress: Etiology and consequences. J Workplace Behav Health 21:89–97. CrossRefGoogle Scholar
  14. Cooper CL, Cartwright S (1997) An intervention strategy for workplace stress. J Psychosom Res 43:7–16. CrossRefGoogle Scholar
  15. Costa A, Rincon JA, Carrascosa C et al (2019) Emotions detection on an ambient intelligent system using wearable devices. Futur Gener Comput Syst 92:479–489. CrossRefGoogle Scholar
  16. Dallman MF, Pecoraro N, Akana SF et al (2003) Chronic stress and obesity: a new view of “comfort food. PNAS 97:325–330. Google Scholar
  17. de Arriba-Pérez F, Caeiro-Rodríguez M, Santos-Gago JM (2016) Collection and processing of data from wrist wearable devices in heterogeneous and multiple-user scenarios. Sensors 16:1538. CrossRefGoogle Scholar
  18. de Arriba-Pérez F, Caeiro-Rodríguez M, Santos-Gago JM (2017) How do you sleep? Using off the shelf wrist wearables to estimate sleep quality, sleepiness level, chronotype and sleep regularity indicators. J Ambient Intell Humaniz Comput 1–21.
  19. de Arriba-Pérez F, Santos-Gago JM, Caeiro-Rodríguez M, Fernández-Iglesias MJ (2018) Evaluation of commercial-off-the-shelf wrist wearables to estimate stress on students. JoVE. Google Scholar
  20. Deberard C, Scott M, Glen I et al (2004) Predictors of academic achievement and retention among college freshmen: a longitudinal study. Coll Stud J 381:66–80Google Scholar
  21. Din S, Paul A (2018) Smart health monitoring and management system: toward autonomous wearable sensing for internet of things using big data analytics. Futur Gener Comput Syst doi. Google Scholar
  22. Dishman RK, Nakamura Y, Garcia ME et al (2000) Heart rate variability, trait anxiety, and perceived stress among physically fit men and women. Int J Psychophysiol 37:121–133. CrossRefGoogle Scholar
  23. Ebbinghaus H (2013) Memory: a contribution to experimental psychology. Ann Neurosci 20:155–156. CrossRefGoogle Scholar
  24. empatica (2016) E4 wristband. Accessed 26 Jun 2017
  25. Espinosa HG, Lee J, Keogh J et al (2015) On the use of inertial sensors in educational engagement activities. Procedia Eng 112:262–266. CrossRefGoogle Scholar
  26. Extremera N, Durán A, Rey L (2007) Inteligencia emocional y su relación con los niveles de burnout, engagement y estrés en estudiantes universitarios. 342:239–256Google Scholar
  27. Fan Q, Wang Y (2010) The real-time realization of filtering of speech with DSP TMS320VC5416 Chip. In: 2010 International Conference on Educational and Information Technology. IEEEGoogle Scholar
  28. García-Ros R, Pérez-González F, Pérez-Blasco J, Natividad LA (2012) Evaluación del estrés académico en estudiantes de nueva incorporación a la universidad Academic stress in first-year college students. 143–154Google Scholar
  29. Gonzáles–Romá V, Schaufeli W, Bakker A (2002) The measurement of burnout and engagement: a confirmatory factor analytic approach. Jou Happ StuGoogle Scholar
  30. Grös DF, Antony MM, Simms LJ, Mccabe RE (2007) Psychometric properties of the state–trait inventory for cognitive and somatic anxiety (STICSA): comparison to the state–trait anxiety inventory (STAI). Psychol Assess 19:369. CrossRefGoogle Scholar
  31. Guo F, Li Y, Kankanhalli MS, Brown MS (2013) An evaluation of wearable activity monitoring devices. In: Proceedings of the 1st ACM international workshop on Personal data meets distributed multimedia - PDM’13. ACM Press, New York, New York, USA, pp 31–34Google Scholar
  32. Hamilton M (1959) The assessment of anxiety states by rating. Br J Med Psychol 32:50–55. CrossRefGoogle Scholar
  33. Harari GM, Lane ND, Wang R et al (2016) Using smartphones to collect behavioral data in psychological science. Perspect Psychol Sci 11:838–854. CrossRefGoogle Scholar
  34. Harari GM, Gosling SD, Wang R et al (2017) Patterns of behavior change in students over an academic term: a preliminary study of activity and sociability behaviors using smartphone sensing methods.
  35. Healey JA (2000) Wearable and automotive systems for affect recognition from physiologyGoogle Scholar
  36. Healey JA, Picard RW (2005) Detecting stress during real-world driving tasks using physiological sensors. IEEE Trans Intell Transp Syst 6:156–166. CrossRefGoogle Scholar
  37. Hernandez J, Morris RR, Picard RW (2011) Call center stress recognition with person-specific models. Springer, Berlin, pp 125–134Google Scholar
  38. Highcharts (2017) Interactive JavaScript charts for your webpage|Highcharts. Accessed 11 Jan 2018
  39. Ibáñez V, Silva J, Cauli O (2018) A survey on sleep assessment methods. PeerJ 6:e4849. CrossRefGoogle Scholar
  40. IDC (2016a) The worldwide wearables in 2015, according to IDC. Accessed 26 Jun 2017
  41. IDC (2016b) Worldwide wearables market increases 67.2% Amid seasonal retrenchment, According to IDC. Accessed 26 Jun 2017
  42. IDC (2016c) Basic wearables soar and smart wearables stall as worldwide wearables market climbs 26.1% in the second quarter. Accessed 26 Jun 2017
  43. IDC (2016d) IDC forecasts wearables shipments to reach 213.6 million units worldwide in 2020 with watches and wristbands driving volume while clothing and eyewear gain traction. Accessed 26 Jun 2017
  44. IDC (2017) IDC forecasts shipments of wearable devices to nearly double by 2021 as smart watches and new product categories gain traction. Accessed 7 May 2018
  45. Jersey (2016) Jersey. Accessed 26 Jun 2017
  46. Karthikeyan P, Murugappan M, Yaacob S (2012) Descriptive analysis of skin temperature variability of sympathetic nervous system activity in stress. J Phys Ther Sci 24:1341–1344. CrossRefGoogle Scholar
  47. Kikhia B, Stavropoulos TG, Meditskos G et al (2015) Utilizing ambient and wearable sensors to monitor sleep and stress for people with BPSD in nursing homes. J Ambient Intell Humaniz Comput 1–13.
  48. Kitsantas A, Winsler A, Huie F (2008) Self-regulation and ability predictors of academic success during college: a predictive validity study. J Adv Acad. Google Scholar
  49. Kompier M, Cooper C (1999) Preventing stress, improving productivity: European case studies in the workplaceGoogle Scholar
  50. Koskimäki H, Mönttinen H, Siirtola P et al (2017) Early detection of migraine attacks based on wearable sensors. In: Proceedings of the 2017 ACM international joint conference on pervasive and ubiquitous computing and proceedings of the 2017 ACM international symposium on wearable computers on—UbiComp’17. ACM Press, New York, New York, USA, pp 506–511Google Scholar
  51. Kothgassner OD, Felnhofer A, Hlavacs H et al (2016) Salivary cortisol and cardiovascular reactivity to a public speaking task in a virtual and real-life environment. Comput Human Behav 62:124–135. CrossRefGoogle Scholar
  52. Lin T, Omata M, Hu W, Imamiya A (2005) Do physiological data relate to traditional usability indexes? In: Proc 17th Aust Conf Comput Interact Citizens Online Considerations Today Futur Comput Interact Spec Interes Gr Aust 1–10Google Scholar
  53. Lovibond S, Lovibond P (1995) Manual for the depression anxiety stress scales. Hum ReprodGoogle Scholar
  54. Lu L (1994) University transition: major and minor life stressors, personality characteristics and mental health. Psychol Med 24:81. CrossRefGoogle Scholar
  55. Lundberg U, Kadefors R, Melin B et al (1994) Psychophysiological stress and emg activity of the trapezius muscle. Int J Behav Med 1:354–370. CrossRefGoogle Scholar
  56. Mario B, Massimiliano M, Chiara M et al (2009) White-coat effect among older patients with suspected cognitive impairment: prevalence and clinical implications. Int J Geriatr Psychiatry 24:509–517. CrossRefGoogle Scholar
  57. Mariotti A (2015) The effects of chronic stress on health: new insights into the molecular mechanisms of brain–body communication. Futur Sci OA 1:fso.15.21. CrossRefGoogle Scholar
  58. Mark H, Ian W, Eibe F (2011) data mining: practical machine learning tools and techniques. Morgan Kaufmann PublishersGoogle Scholar
  59. Maslach C, Jackson SE (1981) The measurement of experienced burnout*. J Occup Behav 2:99–113CrossRefGoogle Scholar
  60. Maslach C, Jackson SE, Schwab RL (1986a) The MBI-EDUCATORS Survey. The MaslachGoogle Scholar
  61. Maslach C, Jackson S, Leiter M (1986b) Maslach Burnout Inventory. Palo AltoGoogle Scholar
  62. Mastrandrea R, Fournet J, Barrat A (2015) Contact patterns in a high school: a comparison between data collected using wearable sensors, contact diaries and friendship surveys. PLoS One 10:e0136497. CrossRefGoogle Scholar
  63. Mayo Clinic Staff (2016) Chronic stress puts your health at risk—Mayo Clinic. Accessed 24 Oct 2018
  64. Microsoft (2015) Microsoft Band SDK. Accessed 26 Jun 2017
  65. Mohr DC, Jorm A, Saeb S et al (2016) The relationship between mobile phone location sensor data and depressive symptom severity.
  66. Mokhayeri F, Akbarzadeh-T M-R, Toosizadeh S (2011) Mental stress detection using physiological signals based on soft computing techniques. In: 2011 18th Iranian conference of biomedical engineering (ICBME). IEEE, pp 232–237Google Scholar
  67. MongoDB (2017) MongoDB for GIANT Ideas | MongoDB. Accessed 26 Jun 2017
  68. Norton PJ (2007) Depression anxiety and stress scales (DASS-21): psychometric analysis across four racial groups. Anxiety Stress Coping 20:253–265. CrossRefGoogle Scholar
  69. Pedrotti M, Mirzaei MA, Tedesco A et al (2014) Automatic stress classification with pupil diameter analysis. Int J Hum Comput Interact 30:220–236. CrossRefGoogle Scholar
  70. Polar (2017) Recovery status|Polar Global. Accessed 26 Jun 2017
  71. Prieto LP, Sharma K, Dillenbourg P, Rodríguez-Triana MJ (2016) Teaching analytics: towards automatic extraction of orchestration graphs using wearable sensors. Proc Sixth Int Conf Learn Anal Knowl 148–157.
  72. Rashkova MR, Ribagin LS, Toneva NG (2012) Correlation between salivary α-amylase and stress-related anxiety. Folia Med (Plovdiv) 54:46–51. CrossRefGoogle Scholar
  73. Reiss S, Peterson RA, Gursky DM, McNally RJ (1986) Anxiety sensitivity, anxiety frequency and the prediction of fearfulness. Behav Res Ther 24:1–8. CrossRefGoogle Scholar
  74. Rincon JA, Costa A, Villarrubia G et al (2018) Introducing dynamism in emotional agent societies. Neurocomputing 272:27–39. CrossRefGoogle Scholar
  75. Sandhu MM, Javaid N, Jamil M et al (2015) Modeling mobility and psychological stress based human postural changes in wireless body area networks. Comput Human Behav 51:1042–1053. CrossRefGoogle Scholar
  76. Sano A, Eng B (2016) Measuring college students’ sleep, stress, mental health and wellbeing with wearable sensors and mobile phones. Massachusetts Institute of TechnologyGoogle Scholar
  77. Santos A de (2012) Design, implementation and evaluation of an unconstrained and contactless biometric system based on hand geometry and stress detection. E.T.S.I. Telecomunicación (UPM)Google Scholar
  78. Schaufeli W, Leiter M (1996) Maslach burnout inventory-general survey. Maslach Burn Invent Man 1:19–26Google Scholar
  79. Selye H (1973) The Evolution of the Stress Concept: The originator of the concept traces its development from the discovery in 1936 of the alarm reaction to modern therapeutic applications of syntoxic and catatoxic hormones. Am Sci 61:692–699Google Scholar
  80. Setz C, Arnrich B, Schumm J et al (2010) Discriminating stress from cognitive load using a wearable EDA device. IEEE Trans Inf Technol Biomed 14:410–417. CrossRefGoogle Scholar
  81. Shimmer Shimmer Galvanic Skin Response Sensor | EDA sensor. Accessed 18 Dec 2018
  82. Spielberger CD, Gorsuch RL, Lushene RE (1970) Manual for the state-trait anxiety inventoryGoogle Scholar
  83. Stahl SE, An H-S, Dinkel DM et al (2016) How accurate are the wrist-based heart rate monitors during walking and running activities? Are they accurate enough? BMJ Open Sport Exerc Med 2:e000106. CrossRefGoogle Scholar
  84. Statista (2017) Fitbit leads global wearables market. Accessed 16 May 2018
  85. Statista (2018) Apple jumps to top of the global wearables market. Accessed 16 May 2018
  86. Stroop JR (1935) Studies of interference in serial verbal reactions. J Exp Psychol 18:643–662. CrossRefGoogle Scholar
  87. Taylor S, Zvolensky MJ, Cox BJ et al (2007) Robust dimensions of anxiety sensitivity: development and initial validation of the Anxiety Sensitivity Index-3. Psychol Assess 19:176–188. CrossRefGoogle Scholar
  88. Tombaugh TN (2006) A comprehensive review of the Paced Auditory Serial Addition Test (PASAT). Arch Clin Neuropsychol 21:53–76. CrossRefGoogle Scholar
  89. Travers CJ, Cooper CL (1997) El Estrés de los profesores: la presión en la actividad docente. PaidósGoogle Scholar
  90. Vizer LM, Zhou L, Sears A (2009) Automated stress detection using keystroke and linguistic features: an exploratory study. Int J Hum Comput Stud 67:870–886. CrossRefGoogle Scholar
  91. Vrijkotte TGM, Van-Doornen LJP, De-Geus EJC (2000) Effects of work stress on ambulatory blood pressure, heart rate, and heart rate variability. Hypertension 35Google Scholar
  92. Wallen MP, Gomersall SR, Keating SE et al (2016) Accuracy of heart rate watches: implications for weight management. PLoS One 11:e0154420. CrossRefGoogle Scholar
  93. Wang R, Chen F, Chen Z et al (2014) StudentLife. In: Proceedings of the 2014 ACM international joint conference on pervasive and ubiquitous computing—UbiComp’14 Adjunct. ACM Press, New York, New York, USA, pp 3–14Google Scholar
  94. Wang R, Harari G, Hao P et al (2015) SmartGPA: how smartphones can assess and predict academic performance of college students.
  95. Wang R, Blackburn G, Desai M et al (2017) Accuracy of wrist-worn heart rate monitors. JAMA Cardiol 2:104. CrossRefGoogle Scholar
  96. Wittchen H-U, Boyer P (1998) Screening for anxiety disorders: sensitivity and specificity of the Anxiety Screening Questionnaire (ASQ—15). Br J PsychiatryGoogle Scholar
  97. wranx (2016) Ebbinghaus and the forgetting curve. Accessed 26 Jun 2017
  98. Xu J, Zhong B (2018) Review on portable EEG technology in educational research. Comput Human Behav 81:340–349. CrossRefGoogle Scholar
  99. Zhai J, Barreto A (2006) Stress detection in computer users based on digital signal processing of noninvasive physiological variables. In: 2006 international conference of the IEEE engineering in medicine and biology society. IEEE, pp 1355–1358Google Scholar
  100. Zhai J, Barreto AB, Craig-Chin C-L (2005) Realization of stress detection using psychophysiological signals for improvement of human–computer interaction. In: Proceedings. IEEE SoutheastCon. IEEE, pp 415–420Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Telematics EngineeringUniversity of VigoVigoSpain

Personalised recommendations